Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 19296
    Prev
    Next
    INDEX
    Explanations

    names and variations of the word "cruise"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¿°
    -0.14
    out
    -0.14
    hood
    -0.14
    outed
    -0.14
    393
    -0.14
    ayment
    -0.14
    casts
    -0.13
     pastoral
    -0.13
    arg
    -0.13
    unes
    -0.13
    POSITIVE LOGITS
    ifix
    0.32
    ible
    0.19
    aders
    0.18
    iate
    0.17
     fixes
    0.17
    ifax
    0.17
    IFORM
    0.17
    ISING
    0.17
    ising
    0.16
    fix
    0.16
    Activations Density 0.008%

    No Known Activations